AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

WINS: Winograd Structured Pruning for Fast Winograd Convolution

Cheonjun Park, Hyun Jae Oh, Mincheol Park, Hyunchan Moon, Minsik Kim, Suhyun Kim, Myung Kuk Yoon, Won Woo Ro

ICCV 2025 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use l2-norm instead of l1-norm as representative value (ablation)WINS · CIFAR-10 ResNet-32 (PR 90%)Top-1 accuracy (%): 91.33 -> 91.84Improved
use Geometric Median instead of l2-norm (ablation)WINS · CIFAR-10 ResNet-56 (PR 90%)Top-1 accuracy (%): 92.08 -> 92.56Improved
use l2-norm instead of Geometric Median (ablation)WINS · CIFAR-10 ResNet-20 (PR 80%)Top-1 accuracy (%): 91.42 -> 91.51Improved
add load balancing across sub-GEMMs (WINS-B over WINS) (ablation)WINS · ResNet-18 ImageNetrelative speedup: 1.15x at 30% PR to 1.43x at 70% PRImproved
add balancing (WINS-B) to WINS (ablation)WINS · ResNet-18 ImageNet (PR 80%)Top-1 accuracy drop: 1.27% drop for WINS-B vs less than 1% for WINSHurt
add adaptive layer-wise selection (WINS-AB over WINS) (ablation)WINS · ResNet-18 ImageNet (PR 80%)speed: approximately 1.2 times fasterImproved
prune 1x1 convolutions with BCBP instead of FPGM (ablation)WINS-AB · Res2Net-50 ImageNet (PR 85%/50%)Top-1 accuracy (%): 75.23 -> 75.87Improved
prune 1x1 convolutions with BCBP instead of FPGM (ablation)WINS-AB · Res2Net-50 ImageNet (PR 65%/30%)Top-1 accuracy (%): 76.16 -> 76.32Improved
use WINS-AB instead of filter pruningResNet-18 · ImageNetaccuracy drop: FP exceeds 2.0% drop from 30% PR; WINS-AB does not exceed 0.6% at 80% PRImproved
use WINS-AB instead of filter pruningResNet-18 and VGG-16 · ImageNetspeedup within 1.5% accuracy drop: 1.84x and 1.27x fasterImproved
use WINS-AB instead of Winograd weight pruningVGG-16 · ImageNet (PR 70%)accuracy: WWP 2.0% higher accuracyHurt
use WINS-AB instead of Winograd weight pruningVGG-16 · ImageNet (PR 84%)speedup: 2.01x faster than Winograd convolutionImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy